DraconicSDXL

CHECKPOINT
Original


Updated:

1.6K

☕ Buy me a coffee: https://ko-fi.com/dracos24

In theory, I only want two SDXL models for my personal use. One for realism/art and one for anime/cartoon/art. In practice, I have way more than I need because there are so many great ones out there.

I merged the three SDXL models I bounced between for "realism" in the hopes that they made a middle ground I could call home.

Juggernaut v7: my go-to for realism for as long as I can remember. It just works.

Artium v1: Even when not deliberately trying to create a certain art form, Artium takes a realistic picture and nudges it slightly into an artistic direction. When I need a quick and easy thumbnail, this is what I turn to.

RealCartoonXL v6: I fell in love with RealCartoon in SD 1.5. Whatever style of animation I wanted, it made the character LORAs better.

So far, it has accomplished what I hoped for. For human subjects, it "airbrushes" the realistic features into a more idealized form, while retaining enough skin texture and realism that they retain a certain amount of natural realism. On the other side though, backgrounds and details (such as trees and mountains in the background), will often take on an oil painting or artistic slant, rather than a photographic blur. This helps lend realism to fantastical creatures, as well.

Version Detail

SDXL 1.0

Project Permissions

Reprinting is strictly prohibited

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated images

  • Use on generation services

  • Sell this model or merges

Comments

Related Posts

Describe the image you want to generate, then press Enter to send.